I am a PhD student in the Carnegie Mellon School of Computer Science and a Machine Learning Researcher at the Software Engineering Institute’s AI Division. My research aims to help create robust, secure, and scalable AI/ML systems. I am especially interested in AI security+safety and currently working on data poisoning and machine unlearning. I’ve been in to triathlons the past few years (I raced a half-Ironman!), and I also like playing chess, skiing, philosophy, and playing soccer, but it’s hard to pin me down to just one thing! You can find my resume here (last updated Jan. 2025).

Publications

  • Memory Adapters Enable Fast, Flexible Knowledge Unlearning in LLMs
    Keltin Grimes, Kevin Kuo, Steven Wu, Virginia Smith, Marissa Connor
    MemFM @ ICMLOral
  • Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning
    Jiahao Zhang, Lujing Zhang, Keltin Grimes, Zhuohao Yu, Gokul Swamy, Zhiwei Steven Wu
    arXiv
  • SoK: Bridging Research and Practice in LLM Agent Security
    Keltin Grimes, Julie Lawler, Robert C. Garrett, Emil Mathew, Marco Christiani, Sara Kingsley, Zhiwei Steven Wu, Nathan VanHoudnos
    SEI White Paper
  • From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming
    Anusha Sinha, Keltin Grimes, James Lucassen, Michael Feffer, Nathan VanHoudnos, Zhiwei Steven Wu, Hoda Heidari
    arXiv
  • What Can Generative AI Red-Teaming Learn from Cyber Red-Teaming?
    Anusha Sinha, James Lucassen, Keltin Grimes, Michael Feffer, Mary Soto, Hoda Heidari, Nathan VanHoudnos
    SEI Technical Report
  • Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
    Keltin Grimes, Marco Christiani, David Shriver, Marissa Connor
    ICLR
  • The SaTML'24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability
    Stephen Casper, Jieun Yun, Joonhyuk Baek, Yeseong Jung, Minhwan Kim, Kiwan Kwon, Saerom Park, Hayden Moore, David Shriver, Marissa Connor, Keltin Grimes, Angus Nicolson, Arush Tagade, Jessica Rumbelow, Hieu Minh Nguyen, Dylan Hadfield-Menell
    arXiv2nd Place Solution
  • Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning(Extended Abstract)
    Keltin Grimes, Collin Abidi, Cole Frank, Shannon Gallagher
    DLSP @ IEEE S&P

Presentations

  • Erasing Hazardous Knowledge from LLMs with Machine Unlearning, Nexus Series: AI x Bio Workshop 1 (invited), November 13, 2025
  • AI Engineering and LLMs, SCADS (invited), June 17, 2024, with Jasmine Ratchford
  • Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning, IEEE S&P DLSP Workshop, May 23, 2024
  • Statistical Validation of Fuel Savings from In-Flight Data Recordings, DATAWorks, April 18, 2024